Multi-vendor robustness analysis of a commercial artificial intelligence system for breast cancer detection

Abstract

Purpose: Population-based screening programs for the early detection of breast cancer have significantly reduced mortality in women, but they are resource intensive in terms of time, cost, and workload and still have limitations mainly due to the use of 2D imaging techniques, which may cause overlapping of tissues, and interobserver variability. Artificial intelligence (AI) systems may be a valuable tool to assist radiologist when reading and classifying mammograms based on the malignancy of the detected lesions. However, there are several factors that can influence the outcome of a mammogram and thus also the detection capability of an AI system. The aim of our work is to analyze the robustness of the diagnostic ability of an AI system designed for breast cancer detection.Approach: Mammograms from a population-based screening program were scored with the AI system. The sensitivity and specificity by means of the area under the receiver operating characteristic (ROC) curve were obtained as a function of the mammography unit manufacturer, demographic characteristics, and several factors that may affect the image quality (age, breast thickness and density, compression applied, beam quality, and delivered dose). Results:The area under the curve (AUC) from the scoring ROC curve was 0.92 (95% confidence interval = 0.89 − 0.95). It showed no dependence with any of the parameters considered, as the differences in the AUC for different interval values were not statistically significant. Conclusion:The results suggest that the AI system analyzed in our work has a robust diagnostic capability, and that its accuracy is independent of the studied parameters.

Advancements in Telehealth: Enhancing Breast Cancer Detection and Health Automation through Smart Integration of IoT and CNN Deep Learning in Residential and Healthcare Settings

“…Moreover, integrating breast cancer into the IoT framework holds significant potential for early detection and monitoring. Although [10][11][12] have delved into IoT applications in educational settings, none of these works addressed Electronic Health Records (EHRs), nor did they highlight the appropriateness of addressing health-related issues in institutional homes through the implementation of health sensors, as proposed in their research.…”

Comparing Prognostic Factors of Cancers Identified by Artificial Intelligence (AI) and Human Readers in Breast Cancer Screening

“…Cancers 2023, 15, 3069 2 of 12 Studies have reported that AI performance is comparable to or might even outperform humans in the interpretation of screening studies [4][5][6][7][8]. In these studies, performance is often assessed in terms of general outcome metrics such as cancer detection rate and recall rate [9], but information on the prognostic features of screen-detected breast cancers is frequently not provided.…”